Abstract
Publications home
ARTEMIS: attention-based retrieval with text-explicit matching implicit similarity
at
| Ginger Delmas, Rafael Sampaio De Rezende, Gabriela Csurka, Diane Larlus |
| Tenth International Conference on Learning Representations (ICLR), virtual event, 25-29 April, 2022 |
| Download |
A multi-modal query, i.e. a query composed of an example image and a companion sentence that modifies it, is a very intuitive way to search for images of a particular fashion article. Previous attempts at tackling this complex task have mostly focused on learning to compose the visual and textual descriptors of the query elements in order to directly compare the resulting representation to those of the candidate fashion target images. Our approach departs from this strategy. We proposes two simple modules which draw inspiration from cross-modal retrieval and image search, respectively. These two research domains have been extensively studied and their successes, when combined, can be used to effectively tackle our task, which lies at the intersection of both families of approaches. We validate our method on several benchmarks with free-form text modifiers and obtain substantial performance improvements on several tasks.
To make robots autonomous in real-world everyday spaces, they should be able to learn from their interactions within these spaces, how to best execute tasks specified by non-expert users in a safe and reliable way. To do so requires sequential decision-making skills that combine machine learning, adaptive planning and control in uncertain environments as well as solving hard combinatorial optimisation problems. Our research combines expertise in reinforcement learning, computer vision, robotic control, sim2real transfer, large multimodal foundation models and neural combinatorial optimisation to build AI-based architectures and algorithms to improve robot autonomy and robustness when completing everyday complex tasks in constantly changing environments.
VISION
The research we conduct on expressive visual representations is applicable to visual search, object detection, image classification and the automatic extraction of 3D human poses and shapes that can be used for human behavior understanding and prediction, human-robot interaction or even avatar animation. We also extract 3D information from images that can be used for intelligent robot navigation, augmented reality and the 3D reconstruction of objects, buildings or even entire cities.
Our work covers the spectrum from unsupervised to supervised approaches, and from very deep architectures to very compact ones. We’re excited about the promise of big data to bring big performance gains to our algorithms but also passionate about the challenge of working in data-scarce and low-power scenarios.
Furthermore, we believe that a modern computer vision system needs to be able to continuously adapt itself to its environment and to improve itself via lifelong learning. Our driving goal is to use our research to deliver embodied intelligence to our users in robotics, autonomous driving, via phone cameras and any other visual means to reach people wherever they may be.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.